Metadata-Version: 2.4
Name: llama-index-llms-modelscope
Version: 0.6.0
Summary: llama-index llms modelscope integration
Author-email: ModelScope <modelscope@list.alibaba-inc.com>
License-Expression: MIT
License-File: LICENSE
Requires-Python: <4.0,>=3.10
Requires-Dist: llama-index-core<0.15,>=0.13.0
Requires-Dist: modelscope[framework]>=1.12.0
Requires-Dist: ms-swift
Requires-Dist: pip
Requires-Dist: sentencepiece
Requires-Dist: torch<3,>=2.1.2
Requires-Dist: transformers[torch]<5,>=4.37.0
Description-Content-Type: text/markdown

# LlamaIndex Llms Integration: ModelScope

## Installation

To install the required package, run:

```bash
!pip install llama-index-llms-modelscope
```

## Basic Usage

### Initialize the ModelScopeLLM

To use the ModelScopeLLM model, create an instance by specifying the model name and revision:

```python
import sys
from llama_index.llms.modelscope import ModelScopeLLM

llm = ModelScopeLLM(model_name="qwen/Qwen3-8B", model_revision="master")
```

### Generate Completions

To generate a text completion for a prompt, use the `complete` method:

```python
rsp = llm.complete("Hello, who are you?")
print(rsp)
```

### Using Message Requests

You can chat with the model by using a list of messages. Here’s how to set it up:

```python
from llama_index.core.base.llms.types import MessageRole, ChatMessage

messages = [
    ChatMessage(
        role=MessageRole.SYSTEM, content="You are a helpful assistant."
    ),
    ChatMessage(role=MessageRole.USER, content="How to make cake?"),
]
resp = llm.chat(messages)
print(resp)
```

### LLM Implementation example

https://docs.llamaindex.ai/en/stable/examples/llm/modelscope/
